Vulnerability Description
PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, MCP HTTP Stream _validate_origin uses request_origin.startswith(allowed), allowing the attacker-controlled localhost.attacker.com HTTP origin to satisfy the localhost allowlist. A webpage can send Content-Type: text/plain requests without preflight and invoke tools/call without an API key, including file writes that persist agent instructions. This issue is fixed in version 4.6.58.
CVSS Score
HIGH
Related Weaknesses (CWE)
References
- https://github.com/MervinPraison/PraisonAI/commit/2f9677abb2ea68eab864ee8b6a828f
- https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.58
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-pvph-5j39-v8
FAQ
What is CVE-2026-55532?
CVE-2026-55532 is a vulnerability with a CVSS score of 7.6 (HIGH). PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, MCP HTTP Stream _validate_origin uses request_origin.startswith(allowed), allowing the attacker-controlled localhost.attacker.com HT...
How severe is CVE-2026-55532?
CVE-2026-55532 has been rated HIGH with a CVSS base score of 7.6/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-55532?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.